SKILLEMALL.ai
GitHub ↗ RU Sign in

BC feishu-doc-scraper

Extract Feishu (Lark) Docs, Wiki pages/collections, spreadsheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API (no LLM rewriting of the body; browser-DOM fallback when lark-cli can't reach the content). Use whenever the source is a Feishu/Lark URL and fidelity matters — 导出飞书文档/合集/妙记转写, 把飞书 wiki/知识库转 markdown, archiving a Feishu collection, exporting a 妙记 transcript, or saving a Feishu page — even if the user only says clipping, archiving, converting, or "save this". Also covers the owner-exported .docx → faithful Markdown path. Document reading includes comments, feedback and all replies in the selected solved scope; Minutes comments are outside this capability.

Not recommendedcritical or high security findings
daymade/claude-code-skills Claude Code author: daymade 20 files body ≈ 6 483 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Extract Feishu (Lark) Docs, Wiki pages/collections, spreadsheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API (no LLM…

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationWordData and analyticsAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
76/100
safety, quality, tests
Safety 60%
72
Quality 40%
81
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

  • high Exfiltration intent-browser-credential-store scripts/download_feishu_images.py:200
    Accesses a browser credential / cookie store
    cookies = brow…ome()
Medium and low: 2
  • medium Obfuscation uni-zero-width scripts/feishu_dom_capture.js:53
    Zero-width / invisible characters (possible hidden text) (6 occurrences)
    return result.replace(/[␀␀]/g, '');
  • medium Obfuscation uni-zero-width scripts/restore_docx_headings.py:54
    Zero-width / invisible characters (possible hidden text) (4 occurrences)
    _ZERO_WIDTH = "␀␀␀␀"

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6483 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 88): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 63/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 7 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 6483 tokens
  • 100Steps. 51 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (25 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 704: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 51 items
  • +4Has examples (8 code blocks)
  • +4Reference files are cited in the instructions (9 of 9)
  • +3All 8 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.